#Humanitarian Tech
2 articles with this tag
Technology
Testing AI Guardrails Across Languages
Researchers tested context-aware AI guardrails across English and Farsi in humanitarian scenarios, finding nuanced performance differences and highlighting the need for language-specific safety evaluations.
4 days ago
Technology
Multilingual LLM Guardrails Tested
Researchers tested how LLM guardrails perform across languages and policy phrasings, revealing significant variations that impact AI safety assessments.
4 days ago